DEV Community: Abhishek Bijjargi

From AI Assisted Exploration to a Wagtail Upgrade Agent

Abhishek Bijjargi — Tue, 31 Mar 2026 12:37:02 +0000

Repositories

Wagtail Upgrade Assistant (Agent): GitHub
Bakerydemo exploration: GitHub

Demo Video

Introduction

Upgrading a Wagtail project is rarely a straightforward process. It involves navigating breaking changes, deprecated APIs, dependency conflicts, and compatibility issues across Python and Django versions.

As part of maintaining the Bakerydemo project, I initially explored how to approach this upgrade problem using an AI assisted workflow. The goal was to understand whether AI could provide a structured and reliable upgrade strategy.

This post documents that journey, starting from prompt based exploration and evolving into a reusable AI agent designed specifically for Wagtail upgrades.

Objective

The goal of this work was to:

Upgrade a Wagtail project to the latest version
Identify and handle deprecations
Ensure dependencies remain secure
Maintain a working CI pipeline after the upgrade

Initial Approach: AI Assisted Planning

I started by providing the following prompt to an AI assistant:

I am a maintainer of the bakerydemo project.

Help me:

Upgrade to the latest Wagtail version

Identify deprecations

Ensure dependencies are secure

Keep CI working after upgrade

Give step by step instructions specific to this project.

The response outlined a structured upgrade strategy, which served as a strong starting point for understanding the process.

Key Insights from the AI

Incremental Upgrades Instead of Direct Jump

Rather than upgrading directly to the latest version, the AI recommended incremental upgrades across major versions.

For example:

Current version to Wagtail 5
Then to Wagtail 6
Finally to Wagtail 7

This reduces risk and simplifies debugging.

Dependency Alignment

A critical requirement is aligning:

Python version
Django version
Wagtail version

Incompatible combinations can lead to installation failures or runtime issues.

Handling Breaking Changes

Common breaking changes included:

Migration from wagtail.core to wagtail
Changes in the panel API
StreamField configuration updates
Removal of legacy admin components

These require manual code updates and cannot be fully automated.

Deprecation Awareness

The AI emphasized identifying deprecated APIs early by enabling warnings and reviewing logs, allowing maintainers to fix issues proactively.

CI Stability

Maintaining CI integrity during upgrades involves:

Updating Python versions
Ensuring migrations run correctly
Verifying static file handling
Running test suites after dependency updates

Limitation of the Initial Approach

While the AI generated a solid plan, it had one limitation:

It was not reusable.

Each time, the process depended on re-entering prompts and manually interpreting results. This made it less practical for repeated use across projects.

From Prompt to Agent: Building a Reusable Solution

To address this, I extended the idea into a dedicated tool:

Wagtail Upgrade Assistant

A domain specific AI agent and CLI tool designed to automate the analysis phase of Wagtail upgrades.

Repository: https://github.com/Abhi090907/Wagtail-Upgrade-Assistant-agent/tree/main

What the Agent Does

The Wagtail Upgrade Assistant transforms the earlier exploration into a reusable workflow.

Project Analysis

Detects Python, Django, and Wagtail versions
Parses dependency files such as requirements.txt

Static Code Analysis

Identifies deprecated patterns such as:
- wagtail.core imports
- legacy edit handlers
- StreamField configuration issues (e.g., missing use_json_field=True)
Uses Python AST for accurate detection

Upgrade Guidance

Suggests incremental upgrade paths
Highlights required code changes

Dependency Audit

Flags outdated or incompatible packages

CI Recommendations

Provides GitHub Actions based suggestions
Ensures compatibility during upgrades

Recent Enhancement

Based on feedback, I extended the analyzer to detect StreamField configuration issues.

The tool now identifies cases where:

use_json_field=True is missing
Deprecated imports such as wagtail.core.fields are used

This makes the agent more aligned with real Wagtail upgrade requirements and improves its practical usefulness for maintainers.

Example Workflow

Run the CLI tool:

wagtail-upgrade-agent ./example_project

The agent generates a structured report including:

Current stack summary
Deprecated API usage with file references
Recommended upgrade path
Required code changes
Dependency updates
CI improvements

Why This Matters

This approach shifts the process from:

Manual interpretation of AI responses

to:

A repeatable and structured upgrade workflow

It allows maintainers to quickly assess upgrade complexity without manually scanning the entire codebase.

Observations

During development and testing, a few practical challenges emerged:

Environment issues such as Python version compatibility
Dependency installation inconsistencies
The need for manual validation despite automated analysis

These highlight that while AI and tooling can assist significantly, human oversight remains essential.

Key Takeaways

A structured upgrade strategy is critical for Wagtail projects
Incremental upgrades reduce risk and complexity
Dependency compatibility must be carefully managed
AI is effective for planning, but tools make it reusable
Combining AI with static analysis creates a practical workflow

Conclusion

Upgrading Wagtail projects involves more than updating dependencies. It requires careful planning, awareness of framework changes, and maintaining system stability.

Starting with an AI assisted exploration provided valuable insights. Extending that into a reusable agent transformed those insights into a practical tool.

This progression from prompt to implementation demonstrates how AI can move beyond assistance and become part of a maintainable development workflow.

Connect

GitHub: GitHub

LinkedIn: LinkedIn

Gmail: abhishekbijjargi4@gmail.com

Using AI Agent Skills to Simplify Wagtail Bakerydemo Maintenance

Abhishek Bijjargi — Mon, 30 Mar 2026 12:46:49 +0000

Building an AI Agent Skill for Wagtail Bakerydemo Maintenance

What is an AI Agent Skill

An AI agent skill is a structured markdown document that gives AI
coding assistants like Claude, Cursor and GitHub Copilot contextual
knowledge about a specific codebase. Instead of the AI having to
read through your entire source code every time you ask a question,
the skill file provides a curated reference covering project
structure, common tasks, conventions and known issues.

Wagtail recently published a blog post about agent skills for
upgrading Wagtail sites. As part of my GSoC 2026 application for
the Demo Website Redesign project, I wrote one specifically for
maintaining the bakerydemo codebase.

Why the Bakerydemo Needs This

The bakerydemo serves two critical purposes for the Wagtail
project. It is the primary demonstration tool for developers and
organisations evaluating Wagtail, and it is the standard local
development environment for Wagtail contributors.

Maintaining it involves recurring tasks like updating dependencies,
managing content fixtures, modifying templates and checking
accessibility. An AI agent skill that understands the bakerydemo
structure means any contributor can get accurate, context-aware
assistance for these tasks without needing deep familiarity with
the codebase first.

What the Skill Covers

The skill I wrote covers the following areas.

Project structure — a complete map of the bakerydemo directory
tree explaining what each folder and file contains and what it is
responsible for.

Common maintenance tasks — step by step guidance for updating
dependencies, adding new content fixtures, modifying templates,
running tests and checking accessibility compliance.

Wagtail specific concepts — explanations of StreamField,
the image library, snippets and search as they are used in the
bakerydemo specifically.

Development environment — how to set up the Docker based
development environment and the simpler local setup.

Pull request guidelines — what is expected when submitting
contributions to the bakerydemo repository.

Common errors and solutions — the most frequent issues
contributors encounter and exactly how to fix them.

How I Built It

I started by spending several hours reading through the bakerydemo
codebase on GitHub. I mapped out the project structure, read through
the models, templates and fixture files, and noted down all the
Wagtail-specific patterns used throughout the project.

I then set up the full bakerydemo development environment locally
using Docker, which gave me hands-on familiarity with the setup
process and the errors that new contributors typically encounter.
I documented these errors and their solutions directly in the skill.

Finally I structured all of this knowledge into a markdown document
following the format that AI coding assistants respond to most
effectively — clear headings, concrete code examples and explicit
step-by-step instructions rather than vague general guidance.

The Skill File

The complete skill is available as a public GitHub Gist here:
GitHub Gist

How to Use It

If you are using Cursor, open the bakerydemo project and paste
the skill content into the Cursor context or reference the gist
URL directly in your prompt.

If you are using Claude, paste the skill content at the start of
your conversation before asking maintenance questions.

Example prompt:

"Using this bakerydemo maintenance skill: GitHub Gist, help me
add a new page type for a Special Offers section. What files
do I need to create or modify?"

The AI will then give you accurate, bakerydemo-specific guidance
referencing the correct file paths, Wagtail conventions and
project structure without needing to read the source code itself.

DEMO

For Claude

Demo Video

For Anti Gravity

Implementation Plan provided by AI

Implementation Plan: Add Special Offers Page Type

Based on the prompt, we are adding a new "Special Offers" section to the existing bakerydemo repository (bakery-demo-skill-test).

User Review Required

Since this introduces a new app into the codebase, please review the plan below.

Once approved, the implementation can be executed step-by-step.

Proposed Changes

Following the SKILL.md guidelines, this involves:

Scaffolding a new Django app within the Wagtail structure

Creating templates using accessible patterns

Validating via test cases

Core Settings

[MODIFY] bakerydemo/settings/base.py

Add 'bakerydemo.special_offers' to INSTALLED_APPS

This ensures Wagtail detects the new models

New App: special_offers

[NEW] bakerydemo/special_offers/__init__.py

Empty file to declare module

[NEW] bakerydemo/special_offers/models.py

SpecialOfferIndexPage → parent container

SpecialOfferPage → individual offer page

Use StreamField for flexible content

Integrate Wagtail image library

Templates

[NEW] templates/special_offers/special_offer_index_page.html

Extend {% extends "base.html" %}

Loop through child pages

Use {% image %} and {% pageurl %}

[NEW] templates/special_offers/special_offer_page.html

Extend base.html

Render StreamField blocks

Include accessibility-friendly structure

Tests

[NEW] bakerydemo/special_offers/tests.py

Basic TestCase

Validate model instantiation

Ensure compatibility with:
python manage.py test bakerydemo.special_offers
Open Questions

Should SpecialOfferPage include:

discount percentage?

expiration date?

or just flexible content?

Verification Plan

Automated:
python manage.py makemigrations special_offers
python manage.py migrate
python manage.py test bakerydemo.special_offers
Accessibility Checklist:

Images must include meaningful alt text

Forms must have proper <label> tags

Ensure WCAG AA contrast compliance

Full keyboard navigation support

Unique and descriptive page titles

Relevance to the GSoC Project

As part of the Demo Website Redesign project I plan to work on
during GSoC 2026, I will be introducing new templates, content
fixtures and possibly new page types. Updating the agent skill
as part of this work means future contributors and maintainers
will have an accurate reference for working with the new structures
using AI assistance.

This is a small contribution now but has compounding value over
time as more contributors use AI coding tools in their workflow.

My GSoC Application

I am applying for Google Summer of Code 2026 with Wagtail for the
Demo Website Redesign project. If you are also going through the
application process feel free to reach out on the Wagtail Slack
or GitHub.

GitHub: GitHub
Dev.to: Dev.to
Wagtail participant file: Wagtail
LinkedIn: Linkedin

Setting Up Wagtail as a GSoC 2026 Applicant — From Zero to Dev Environment

Abhishek Bijjargi — Mon, 23 Mar 2026 13:43:50 +0000

Setting Up Wagtail as a GSoC 2026 Applicant — From Zero to Dev Environment

Who am I

My name is Abhishek Bijjargi and I am a first year B.Tech Computer
Science student at COEPTech University, Pune, India. I am applying
for Google Summer of Code 2026 with Wagtail and this post documents
my complete journey of setting up the Wagtail development environment
from scratch on Windows — including every challenge I hit and how I
solved it.

Why Wagtail

Wagtail is one of the most widely used open source CMS platforms built
on top of Django and Python. As someone who has built full stack
projects using Django — including CyberVision, a cybersecurity scanning
platform — Wagtail felt like a natural fit for GSoC 2026. The community
is welcoming, the codebase is mature and well structured, and the
project ideas are genuinely impactful.

Part 1 — Completing the Django Tutorial

Before touching Wagtail, I completed the official Django 6.0 tutorial
which is a mandatory requirement for Wagtail GSoC applicants. This
covered building a fully functional polls web application from scratch.

What the tutorial covered

Setting up a Django project and app structure
Creating models and running migrations
Building views, templates and URL routing
Setting up the Django admin panel
Adding static files and CSS styling
Writing automated tests

Running it

After completing the tutorial my polls app was live at
http://127.0.0.1:8000/polls/ with a green background, working
voting functionality and a fully functional admin panel.

Wagtail Bakery tutorial with admin panel (video)

The completed Django tutorial repository is here:
GitHub

Part 2 — Wagtail Bakery Demo Tutorial

With Django basics solid, I moved to the Wagtail Bakery Demo — the
official demonstration site that Wagtail requires all GSoC applicants
to set up.

Step 1 — Clone the Bakery Demo

git clone https://github.com/wagtail/bakerydemo.git
cd bakerydemo

Step 2 — Create and activate a virtual environment

python -m venv venv
venv\Scripts\activate

Step 3 — Install dependencies

pip install -r requirements/development.txt

This takes a few minutes as it pulls in Wagtail and all its
dependencies.

Step 4 — Create local config files

copy bakerydemo\settings\local.py.example bakerydemo\settings\local.py
copy .env.example .env

Step 5 — Set up the database and load demo data

python manage.py migrate
python manage.py load_initial_data

Step 6 — Run the server

python manage.py runserver

The Wagtail Bakery demo site was now live at http://127.0.0.1:8000/
with a full bakery website including bread listings, blog posts and
location pages.

Admin credentials: username admin / password changeme

Part 3 — Wagtail Dev Environment Setup via Docker

This was the most involved part. Setting up Wagtail's actual source
code for contributing requires Docker on Windows. Here is the exact
process I followed.

Why Docker

On Windows, Wagtail's development environment is best set up using
Docker. The docker-wagtail-develop repository provides everything
needed — the Wagtail source code, the bakery demo site, Elasticsearch,
PostgreSQL and a frontend builder all wired together.

Step 1 — Clone the required repositories

mkdir wagtail-contrib
cd wagtail-contrib
git clone https://github.com/wagtail/docker-wagtail-develop.git wagtail-dev
cd wagtail-dev
git clone https://github.com/wagtail/bakerydemo.git
git clone https://github.com/wagtail/wagtail.git

Step 2 — Clone the missing Willow library

This step is not documented anywhere officially but is required.
Without it Docker compose will fail with a /libs/Willow: not found
error.

mkdir libs
cd libs
git clone https://github.com/wagtail/Willow.git Willow
cd ..

Step 3 — Start Docker containers

docker compose up

This downloads and builds all required images including Elasticsearch,
PostgreSQL, the Node.js frontend builder and the Python web container.
The first run takes around 15 to 20 minutes — be patient here.

Step 4 — Run migrations and load data

In a second terminal window while the first is still running:

docker compose exec web python manage.py migrate
docker compose exec web python manage.py load_initial_data

Step 5 — Verify the setup

Visited http://localhost:8000/ and saw the Wagtail Bakery site
running on my local copy of Wagtail's source code.

This means any edits I make to the Wagtail source code in the
wagtail folder will immediately reflect on the running site —
perfect for contributing.

Challenges I Faced and How I Fixed Them

Challenge 1 — setup.sh not running on Windows

The ./setup.sh script failed in Command Prompt with:

'.' is not recognized as an internal or external command

Fix: Manually cloned each required repository individually instead
of relying on the shell script.

Challenge 2 — Missing Willow library

Docker compose failed with:

/libs/Willow: not found

Fix: Manually cloned the Willow repository from GitHub into a libs
folder inside the wagtail-dev directory.

Challenge 3 — Wagtail admin CSS missing warning

Got a warning about missing admin CSS files on startup. This resolved
automatically once the frontend Docker container finished building the
static assets — which takes around 20 minutes on first run.

What I Learned

Setting up a production-grade open source development environment on
Windows is significantly different from setting up a personal project.
It requires understanding Docker containers, volume mounts, service
dependencies and multi-container orchestration. This experience gave
me real confidence that I can navigate Wagtail's codebase and
contribute meaningfully.

My Projects

As part of my GSoC 2026 application preparation I have also built:

CyberVision — AI powered cybersecurity scanning platform using
Django, OpenCV, Docker, Celery and AI integrations
GitHub

LendSynthetix — Multi-agent AI credit underwriting engine using
LangGraph, XGBoost and RAG
GitHUb
Django Polls Tutorial
GitHub

Next Steps

Find and fix a good first issue in the Wagtail repository
Submit my GSoC 2026 proposal draft for mentor feedback
Continue engaging with the Wagtail community on Slack

Connect

GitHub: GitHub
Email: abhishekbijjargi4@gmail.com

If you are also applying for GSoC 2026 with Wagtail feel free to
reach out — happy to compare notes!

DEV Community: Abhishek Bijjargi

From AI Assisted Exploration to a Wagtail Upgrade Agent

Repositories

Demo Video

Introduction

Objective

Initial Approach: AI Assisted Planning

Key Insights from the AI

Incremental Upgrades Instead of Direct Jump

Dependency Alignment

Handling Breaking Changes

Deprecation Awareness

CI Stability

Limitation of the Initial Approach

From Prompt to Agent: Building a Reusable Solution

Wagtail Upgrade Assistant

What the Agent Does

Project Analysis

Static Code Analysis

Upgrade Guidance

Dependency Audit

CI Recommendations

Recent Enhancement

This makes the agent more aligned with real Wagtail upgrade requirements and improves its practical usefulness for maintainers.

Example Workflow

Why This Matters

Observations

Key Takeaways

Conclusion

Connect

Using AI Agent Skills to Simplify Wagtail Bakerydemo Maintenance

Building an AI Agent Skill for Wagtail Bakerydemo Maintenance

What is an AI Agent Skill

Why the Bakerydemo Needs This

What the Skill Covers

How I Built It

The Skill File

How to Use It

DEMO

For Claude

For Anti Gravity

Implementation Plan provided by AI

Implementation Plan: Add Special Offers Page Type

User Review Required

Proposed Changes

Core Settings

New App: special_offers

Templates

Tests

Open Questions

Verification Plan

Relevance to the GSoC Project

My GSoC Application

Setting Up Wagtail as a GSoC 2026 Applicant — From Zero to Dev Environment

Setting Up Wagtail as a GSoC 2026 Applicant — From Zero to Dev Environment

Who am I

Why Wagtail

Part 1 — Completing the Django Tutorial

What the tutorial covered

Running it

Part 2 — Wagtail Bakery Demo Tutorial

Step 1 — Clone the Bakery Demo

Step 2 — Create and activate a virtual environment

Step 3 — Install dependencies

Step 4 — Create local config files

Step 5 — Set up the database and load demo data

Step 6 — Run the server

Part 3 — Wagtail Dev Environment Setup via Docker

Why Docker

Step 1 — Clone the required repositories

Step 2 — Clone the missing Willow library

Step 3 — Start Docker containers

Step 4 — Run migrations and load data

Step 5 — Verify the setup

Challenges I Faced and How I Fixed Them

Challenge 1 — setup.sh not running on Windows

Challenge 2 — Missing Willow library

Challenge 3 — Wagtail admin CSS missing warning

What I Learned

My Projects

New App: `special_offers`